| 基于深度学习的石化机组轴承故障诊断综述 |
| |
| 引用本文： | 刘鸣慧,熊建斌,苏乃权,李春林,岑健,张钰妤. 基于深度学习的石化机组轴承故障诊断综述[J]. 机床与液压, 2023, 51(6): 171-180 |
| |
| 作者姓名： | 刘鸣慧 熊建斌 苏乃权 李春林 岑健 张钰妤 |
| |
| 作者单位： | 广东技术师范大学自动化学院, 广东广州 510665;广州市智慧建筑设备信息集成与控制重点实验室, 广东广州 510665;广东石油化工学院机电学院, 广东茂名 525000 |
| |
| 基金项目： | 国家自然科学基金面上项目（62073090);国家自然科学基金-广东省联合基金重点项目（U22A20221）;广东省科技创新战略专项资金项目（pdjh2022b0301）;广东省教育厅重大项目（2020ZDZX201）;广东省教育厅重点项目（219KZDXM020）;广东省自然科学基金面上项目（2023A1515011423） |
| |
| 摘 要： | 作为石化机组的重要组成部分,轴承发生故障将导致机械运转故障进而影响企业经济效益,故而研究石化机组轴承故障预测、故障诊断具有重大意义。介绍故障诊断中早期基于信号处理的轴承故障诊断方法,阐述应用广泛的深度学习(包括卷积神经网络、迁移学习)等模型在石化机组轴承故障诊断中的应用,并展望基于人工智能的石化机组轴承故障诊断应用。
|
| 关 键 词： | 轴承故障诊断 机器学习 特征提取 卷积神经网络 迁移学习 |
Review of Bearing Fault Diagnosis of Petrochemical Units Based on Deep Learning |
| |
| LIU Minghui,XIONG Jianbin,SU Naiquan,LI Chunlin,CEN Jian,ZHANG Yuyu. Review of Bearing Fault Diagnosis of Petrochemical Units Based on Deep Learning[J]. Machine Tool & Hydraulics, 2023, 51(6): 171-180 |
| |
| Authors: | LIU Minghui XIONG Jianbin SU Naiquan LI Chunlin CEN Jian ZHANG Yuyu |
| |
| Abstract: | As an important part of rotating machinery, bearing fault will cause mechanical operation failure, which can affect the economic benefits of the enterprise. Therefore, it is important to study the prediction and diagnosis of bearing fault. The early signal processing method in fault diagnosis was introduced. The application of widely used deep learning, including convolutional neural network, transfer learning in the fault diagnosis of petrochemical unit bearing was explained. The application of artificial intelligence-based bearing fault diagnosis of petrochemical units was forecasted. |
| |
| Keywords: | Bearing fault diagnosis Machine learning Feature extraction Convolutional neural network Transfer learning |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《机床与液压》浏览原始摘要信息 |
|
点击此处可从《机床与液压》下载全文 |
|
